Chi-Huang Lu

Adaptive Predictive Control With Recurrent Neural Network for Industrial Processes: An Application to Temperature Control of a Variable-Frequency Oil-Cooling Machine

An adaptive predictive control with recurrent neural network prediction for industrial processes is presented. The neural predictive control law with integral action is derived based on the minimization of a modified predictive performance criterion. The stability and steady-state performance of the closed-loop control system are well studied. Numerical simulations reveal that the proposed control gives satisfactory tracking and disturbance rejection performance for two illustrative nonlinear systems with time-delay. Experimental results for temperature control of a variable-frequency oil-cooling process show the efficacy of the proposed method for industrial processes with set-points changes and load disturbances.

Wavelet Fuzzy Neural Networks for Identification and Predictive Control of Dynamic Systems

This paper presents a wavelet fuzzy neural network (WFNN) structure for identifying and controlling nonlinear dynamic systems. The proposed WFNN is constructed on the base of a set of fuzzy rules. Each rule includes a wavelet function in the consequent part of the rules. A training algorithm adopting a gradient descent method is employed to identify the unknown parameters in the WFNN. For the control problem, a WFNN-based predictive control (WFNNPC) law is derived via a generalized predictive performance criterion, and the control algorithm is proven to guarantee the convergence of the WFNNPC controller. The conditions of the stability analysis of the resulting control system are presented based on the Lyapunov stability theorem. Finally, the WFNN is applied in numerical simulations and experiments (identification and control of nonlinear dynamic systems and a physical positioning mechanism). The results confirm the effectiveness of the WFNN.

Multivariable self-tuning temperature control for plastic injection molding process

This paper develops a multivariable self-tuning predictive control for improving set-point tracking performance, disturbance rejection, and robustness of a temperature control system for an extruder barrel in a plastic injection molding process. The stochastic discrete-time multivariable mathematical model is built and its unknown system parameters are identified by using the recursive least-squares estimation method. The multivariable predictive control is derived based on the minimization of a generalized predictive performance criterion. A real-time self-tuning control algorithm is proposed and then implemented by using a digital signal processor (DSP) TMS320C31 from Texas Instruments. Experimental results are used to show the feasibility and effectiveness of the proposed method.

Adaptive decoupling predictive temperature control for an extrusion barrel in a plastic injection molding process

This paper presents an adaptive decoupling temperature control for an extrusion barrel in a plastic injection molding process. After establishing a stochastic polynomial matrix model of the system, a corresponding decoupling system representation was then developed. The decoupling control design was derived based on the minimization of a generalized predictive performance criterion. The set-point tracking, disturbance rejection, and robustness capabilities of the proposed method can be improved by appropriate adjustments to the tuning parameters in the criterion function. A real-time control algorithm, including the recursive least-squares method, is proposed which was implemented using a digital signal processor TMS320C31 from Texas Instruments. Through the experimental results, the proposed method has been shown to be powerful under set-point changes, load disturbances, and significant plant uncertainties. The proposed control law is shown to be less computational and more effective than other well-known multivariable control strategies, and more powerful than single-loop temperature-zone control policies.

Design and Application of Stable Predictive Controller Using Recurrent Wavelet Neural Networks

This paper presents a design methodology for stable predictive control of nonlinear discrete-time systems via recurrent wavelet neural networks (RWNNs). This type of controller has its simplicity in parallelism to conventional generalized predictive control design and efficiency to deal with complex nonlinear dynamics. A mathematical model using RWNN is constructed, and a learning algorithm adopting a recursive least squares is employed to identify the unknown parameters in the consequent part of the RWNN. The proposed control law is derived based on the minimization of a modified predictive performance criterion. Two theorems are presented for the conditions of the stability analysis and steady-state performance of the closed-loop systems. Numerical simulations reveal that the proposed control gives satisfactory tracking and disturbance rejection performances. Experimental results for position control of a positioning mechanism show the efficacy of the proposed method with setpoint changes.

FUZZY SUPERVISORY PREDICTIVE PID CONTROL OF A PLASTICS EXTRUDER BARREL

Abstract The paper describes the design of single‐loop fuzzy supervisory predictive PID controllers for a plastics extruder barrel. A fuzzy supervisory shell is proposed to improve the set‐point tracking performance of the proposed PID method by appropriate adjustment of the weighting term for the control effort. Experimental results show that the proposed method is capable of giving a good result on the barrel.

Predictive Control Based on Recurrent Neural Network and Application to Plastic Injection Molding Processes

This paper presents a predictive control based on recurrent neural network (RNN) for a class of nonlinear systems and investigates its application to temperature control of plastic injection molding processes. The RNN is used as a model identifier for approximating the nonlinear discrete-time systems and the multivariable predictive control based on the RNN is derived from a generalized predictive performance criterion. The adaptive learning rates of the RNN model and the controller are investigated via the discrete Lyapunov stability theorem, which are respectively used to guarantee the convergences of both the RNN model and the predictive controller. Finally, numerical simulations and experimental results are provided to demonstrate the effectiveness of the proposed control strategy under setpoint changes and bounded disturbances.

Predictive control using recurrent neural networks for industrial processes

Abstract The paper presents a design methodology for predictive control of industrial processes via recurrent neural networks (RNNs). A discrete‐time mathematical model using RNN is established and a multi‐step neural predictor is then constructed. With the predictor, a neural predictive control (NPC) law is developed from the generalized predictive performance criterion. Both the RNN model and the NPC controller are proven convergent based on Lyapunov stability theory. Two examples of a nonlinear process system and a physical variable‐frequency oil‐cooling machine are used to demonstrate the effectiveness of the proposed control method. Through the experimental results, the proposed method has been shown capable of giving satisfactory performance for industrial processes under setpoint changes, external disturbances and load changes.

MIMO neural-network predictive controller design

This paper presents a neural-network predictive control for a class of multi-input multi-output (MIMO) nonlinear systems with time-delay. The MIMO neural-network predictive control law is developed based on the minimization of a generalized predictive performance criterion and the stability of the closed-loop control system is investigated as well. Simulation results reveals that the proposed control gives satisfactory tracking and disturbance rejection performance for the illustrative multivariable systems. Experimental results for heating process of a plastics injection molding machine are performed which have shown efficacy of the proposed method under the condition of set-points and significant plant uncertainties.

Model-reference predictive control using recurrent neural network: an application to temperature control of variable-frequency oil-cooling processes

A model-reference predictive control using recurrent neural network is presented for a class of nonlinear industrial processes. The neural control law is developed to minimize a cost function based on the predictive performance criterion and model reference scheme. A real-time adaptive control algorithm, including a neural predictor and model-reference neural predictive controller, is proposed. The adaptive learning rates for both the neural predictor and controller are chosen based on Lyapunov stability theory. Numerical simulations reveal that the proposed control method gives satisfactory tracking and disturbance rejection performance for two illustrate nonlinear discrete time systems. Experimental results for the temperature control of a variable-frequency oil-cooling machine have shown the efficacy of the proposed controller under the condition of set-points changes and external disturbances.